A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox.

The tool accepts client-controlled parameters (datacol, timestampcol, and idcols) as plain strings and interpolates them unescaped via fmt.Sprintf directly into a generated AI.FORECAST table-valued SELECT statement. While MCP Toolbox utilizes an allowedDatasets mechanism to restrict queries, this defense only validates the historydata parameter; the final assembled query is executed without re-validation.

An attacker can break out of the string literal fields (such as timestampcol) to inject a valid multi-statement or cross-dataset query block. This allows an unauthorized user to bypass the operator-configured allowedDatasets boundary and read arbitrary BigQuery tables.

An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers.

While the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol versions (2025-06-18, 2025-03-26, and 2024-11-05) omit this check. An authenticated client with low-privilege tokens (e.g., read) can bypass the intended per-tool scope restrictions and execute high-privilege tools (e.g., admin) simply by specifying an older protocol version in the MCP-Protocol-Version header, or by omitting the header entirely (which causes the server to default to the vulnerable 2024-11-05 handler).

Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-api flag is active.